three-minds

What problem does it solve?

It solves the problem of getting reliable outcomes for complex code and design tasks by coordinating multiple specialized AI agents that can read and modify the same codebase and iteratively converge on agreement.

Core Features & Use Cases

• Multi-agent collaboration loop: Three agents sequentially review, implement, and vote using a shared working directory.
• Unified model access via claude-code-skill: Route Claude/GPT/Gemini through a consistent agent framework with optional proxy support.
• Preset workflows: Use built-in configurations like default collaboration, multi-model collaboration, and code-review triads for different project goals.
• Practical use cases: Code review, refactoring, feature design-to-implementation, bug fixing, and documentation improvements.

Quick Start

Run three-minds with your task and a target project directory, for example: three-minds "Review all code in src/ and propose fixes, then implement improvements" --dir ./your-project.